© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162428
    Prev
    Next
    INDEX
    Explanations

    pediatric

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moth
    -0.27
    åŀ¢
    -0.27
     Beginner
    -0.25
    æ¢Ń
    -0.25
    ing
    -0.25
     Beginners
    -0.25
    æīĵæ³ķ
    -0.25
    ftype
    -0.24
    иÑĩ
    -0.24
    caff
    -0.24
    POSITIVE LOGITS
    NBC
    0.28
     treat
    0.28
    Inform
    0.25
    天æīį
    0.25
    èĪ«
    0.25
     ups
    0.25
    DIC
    0.25
     treating
    0.25
    spl
    0.24
    å°ıæľĭåıĭ
    0.24
    Activations Density 0.018%

    No Known Activations